论文标题
SDOD：通过深度进行实时分割和检测3D对象
SDOD:Real-time Segmenting and Detecting 3D Object by Depth
论文作者
论文摘要
大多数现有的实例细分方法仅专注于提高性能，不适合诸如自动驾驶之类的实时场景。本文提出了一个实时框架，该框架通过深度分割和检测3D对象。该框架由两个并行分支组成：一个例如分割，另一个用于对象检测。我们将对象的深度离散为深度类别，并将实例分割任务转换为像素级分类任务。蒙版分支预测像素级深度类别，3D分支指示实例级别的深度类别。我们通过分配与每个实例具有相同深度类别的像素来产生实例掩码。此外，为了解决KITTI数据集中蒙版标签和3D标签之间的不平衡，我们引入了自动保管模型生成的粗蒙版，以增加样品。在具有挑战性的Kitti数据集上的实验表明，在分割速度和3D检测速度上，我们的方法优于LKLNET约1.8倍。
Most existing instance segmentation methods only focus on improving performance and are not suitable for real-time scenes such as autonomous driving. This paper proposes a real-time framework that segmenting and detecting 3D objects by depth. The framework is composed of two parallel branches: one for instance segmentation and another for object detection. We discretize the objects' depth into depth categories and transform the instance segmentation task into a pixel-level classification task. The Mask branch predicts pixel-level depth categories, and the 3D branch indicates instance-level depth categories. We produce an instance mask by assigning pixels which have the same depth categories to each instance. In addition, to solve the imbalance between mask labels and 3D labels in the KITTI dataset, we introduce a coarse mask generated by the auto-annotation model to increase samples. Experiments on the challenging KITTI dataset show that our approach outperforms LklNet about 1.8 times on the speed of segmentation and 3D detection.
